Question Answering on AIT-QA OOD (test)
76.71AccuracyQwen3-VL-8B-DISCO
Evaluation Results
| Method | Links | |
|---|---|---|
| Qwen3-VL-8B-DISCOReasoning Strategy=Table-GLS, # TIR=02026.02 | 76.71 | |
| Qwen3-VL-8B-DISCOReasoning Strategy=DA, # TIR=02026.02 | 75.73 | |
| Qwen3-VL-8BReasoning Strategy=DA, # TIR=02026.02 | 71.04 | |
| MiniCPM-V-2.6 8BReasoning Strategy=HIPPO, # TIR=55.2K2026.02 | 66.14 | |
| Gemma3n-E4B-DISCOReasoning Strategy=DA, # TIR=02026.02 | 64.77 | |
| Gemma3n-E4B-DISCOReasoning Strategy=Table-GLS, # TIR=02026.02 | 59.1 | |
| GPT-4o-miniReasoning Strategy=DA, # TIR=02026.02 | 54.01 | |
| Gemma3n-E4BReasoning Strategy=DA, # TIR=02026.02 | 52.25 | |
| Table-LLaVA 13BReasoning Strategy=SFT, # TIR=82K2026.02 | 6.06 | |
| Table-LLaVA 7BReasoning Strategy=SFT, # TIR=82K2026.02 | 5.48 |